pages/5_conclusion.py

import streamlit as st
from streamlit_extras.badges import badge
import plotly.express as px
import pandas as pd

# Set page configuration
st.set_page_config(
    page_title="Conclusion | CV Journey",
    page_icon="✅",
    layout="wide",
    initial_sidebar_state="expanded",
)

# Title and introduction
st.header("✅ Key Takeaways & Future Directions")

st.markdown(
    """
### My Computer Vision Journey: Connecting the Dots

Throughout this presentation, we've explored different facets of my journey in Computer Vision - from robotics and
autonomous systems to deep learning frameworks and cutting-edge VLMs for document analysis.

What connects these diverse projects is a progression of skills, knowledge, and application complexity that
reflects the broader evolution of the computer vision field itself.
"""
)

# Core knowledge areas
st.markdown("---")
st.subheader("Core Knowledge Areas")

col1, col2, col3 = st.columns(3)

with col1:
    st.markdown(
        """
    ### Computer Vision Fundamentals
    
    - Image processing and filtering techniques
    - Feature detection and tracking
    - Camera calibration and homography
    - Geometric transformations
    - Color spaces and thresholding
    - Motion estimation and optical flow
    - Object detection techniques
    """
    )

with col2:
    st.markdown(
        """
    ### Deep Learning for Vision
    
    - Convolutional Neural Networks (CNNs)
    - Model architecture design principles
    - Training and optimization strategies
    - Transfer learning and fine-tuning
    - Object detection frameworks
    - Vision Transformers (ViT)
    - Vision-Language Models (VLMs)
    """
    )

with col3:
    st.markdown(
        """
    ### MLOps & Production Engineering
    
    - Dataset engineering and annotation
    - Hyperparameter optimization
    - Model conversion and optimization
    - Inference server deployment
    - Performance benchmarking
    - Integration with larger systems
    - Monitoring and maintenance
    """
    )

# Key experiences by project
st.markdown("---")
st.subheader("Key Experiences by Project")

project_tabs = st.tabs(
    ["Black Bee Drones", "Asimo Foundation", "CafeDL", "Tech4Humans"]
)

with project_tabs[0]:
    col1, col2 = st.columns(2)

    with col1:
        st.markdown(
            """
        ### Black Bee Drones
        
        **Technical Skills:**
        - Real-time image processing
        - Control systems integration (PID)
        - Vision-based, indoor navigation
        - Marker detection and tracking
        - Line following algorithms
        
        **Soft Skills:**
        - Teamwork in a multidisciplinary environment
        - Working under competition pressure
        - Quick prototyping and iteration
        - Technical presentation
        """
        )

    with col2:
        st.markdown(
            """
        ### Key Lessons
        
        1. **Robustness Over Perfection:** In the real world, perception systems must handle varying conditions and edge cases.
        
        2. **System Integration Challenges:** Computer vision is just one piece of a complex autonomous system.
        
        3. **Resource Constraints:** Balancing computational load with real-time response requirements.
        
        4. **Testing is Critical:** Simulation testing before real flights saves time and prevents crashes.
        
        5. **Iterative Development:** Start simple, verify, then add complexity incrementally.
        """
        )

with project_tabs[1]:
    col1, col2 = st.columns(2)

    with col1:
        st.markdown(
            """
        ### Asimo Foundation
        
        **Technical Skills:**
        - Computer vision for educational applications
        - Hand and gesture recognition
        - Hardware integration (Arduino, servos)
        - Real-time control systems
        - Simple UI development
        
        **Soft Skills:**
        - Teaching complex concepts to beginners
        - Project planning for educational contexts
        - Adapting technical solutions to limited resources
        - Public speaking and demonstration
        """
        )

    with col2:
        st.markdown(
            """
        ### Key Lessons
        
        1. **Accessibility Matters:** Technology should be approachable for beginners with appropriate scaffolding.
        
        2. **Engagement Through Interactivity:** Visual, hands-on applications provide immediate feedback and motivation.
        
        3. **Simplified Interfaces:** Complex technology can be presented through simplified interfaces.
        
        4. **Project-Based Learning:** Students learn best when working toward tangible, interesting goals.
        
        5. **Educational Impact:** Computer vision can be a gateway to broader STEM interest.
        """
        )

with project_tabs[2]:
    col1, col2 = st.columns(2)

    with col1:
        st.markdown(
            """
        ### CafeDL
        
        **Technical Skills:**
        - Deep understanding of neural network architectures
        - Backpropagation and gradient calculation
        - Convolutional operations implementation
        - Software architecture and design patterns
        - Algorithm optimization
        
        **Soft Skills:**
        - Independent research and learning
        - Technical documentation writing
        - Project planning and execution
        - Problem decomposition
        """
        )

    with col2:
        st.markdown(
            """
        ### Key Lessons
        
        1. **First Principles Matter:** Building ML systems from scratch provides deep understanding of the fundamentals.
        
        2. **Software Design Matters:** Good architecture makes complex systems maintainable and extensible.
        
        3. **Mathematics Underlies Everything:** Strong mathematical foundation is essential for ML implementation.
        
        4. **Performance Engineering:** Optimization requires understanding both mathematical and computing constraints.
        
        5. **Documentation is Critical:** Clear APIs and documentation are as important as the code itself.
        """
        )

with project_tabs[3]:
    col1, col2 = st.columns(2)

    with col1:
        st.markdown(
            """
        ### Tech4Humans
        
        **Technical Skills:**
        - State-of-the-art model selection and evaluation
        - Dataset engineering and curation
        - Hyperparameter optimization
        - Production deployment pipelines
        - Fine-tuning large models
        - Benchmarking and evaluation
        
        **Soft Skills:**
        - Project management
        - Client communication
        - Technical writing
        - Presentation of complex results
        - Collaboration in a business environment
        """
        )

    with col2:
        st.markdown(
            """
        ### Key Lessons
        
        1. **Problem Definition is Critical:** Understanding business requirements before technical solutions.
        
        2. **Data Quality Trumps Model Complexity:** Better data often yields better results than more complex models.
        
        3. **Production Readiness:** Considerations beyond model accuracy include inference speed, resource usage, and maintainability.
        
        4. **Evaluation Methodology:** Careful evaluation with appropriate metrics is essential for comparing approaches.
        
        5. **Generalization Challenges:** Models may perform differently on out-of-distribution data, requiring careful testing.
        """
        )


# Thank you and Q&A
st.markdown("---")
st.markdown("## Thank You for Your Attention!")

st.markdown(
    """
I hope this presentation has given you an overview of my journey into the world of Computer Vision and that you may have gained some insight or even learned something from it as well.

I am excited to continue exploring this field and expanding my knowledge.

Feel free to reach out if you have any questions or would like to discuss computer vision or machine learning further!
"""
)

# Add some fun at the end
st.balloons()